Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

introducing rumik oss 1 india's first state of the art open source, fully pre-trained voice model capable of speaking 20+ languages trained on only 66k hours of data, it beats even the top closed models on multiple benchmarks including emotion realism weights are now live 👇🏻

rohan

4,889 subscribers

100,771 Aufrufe • vor 12 Tagen •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

47 Kommentare

Profilbild von rohan

rohanvor 12 Tagen

rumik oss 1 is a 3 billion parameter open weights text to speech model it can speak in indian english, hindi, telugu, tamil, kannada, bengali, punjabi and switches between them mid-sentence, and takes delivery instructions in plain text full research blog - download the weights on hugging face -

Profilbild von rohan

rohanvor 12 Tagen

describe how you want the model to sound like, and it will follow those instructions here are some examples 👇🏻

Profilbild von rohan

rohanvor 12 Tagen

along with the model, we are also open sourcing two of our internal benchmarks 1. indic-emo this benchmark tests can a model hold an emotion through code-switched speech? 100 prompts, each mixing two to five of our seven languages, equal coverage of happy, sad, angry, excited and professional. three judge models score anonymized clips on a five-point rubric covering tone, dynamics, phrasing and sustained expression. rumik oss 1 comfortably beats @cartesia, @ElevenLabs and only @GeminiApp is better and by a big margin it was expected given gemini 3.1 flash tts must be trained on 1000x more data compared to rumik oss 1 is only trained on 66k hours in total

Profilbild von rohan

rohanvor 12 Tagen

2. nova this benchmark measures precise delivery of emotions for eg - if you ask for a laugh at word seven, does it land at word seven? 149 english prompts, one vocalization each at a specified word position, seven systems, three synthesis runs. three detectors check position-correct rendering. benchmark + protocol ->

Profilbild von rohan

rohanvor 12 Tagen

on WER (word error rate) and CER (character error rate) rumik oss 1 tops odia, konkani, maithili while comes second in assamese, kannada, nepali, malyalam

Profilbild von rohan

rohanvor 12 Tagen

rumik oss 1 comes with CC BY-NC 4.0 license plus an acceptable use addendum. that makes it open weights for research and non-commercial use, speech research, benchmarking, teaching, finetuning for experiments. you can share the weights and your adaptations under the same terms, keeping attribution, license links and a note of what you changed.

Profilbild von Soumith Chintala

Soumith Chintalavor 12 Tagen

congrats to the @rumik_ai team. looks like a good first attempt. hope to see rapid iterations.

Profilbild von rohan

rohanvor 12 Tagen

@rumik_ai thanks a ton @soumithchintala

Profilbild von Arpan (Locked In ARC)

Arpan (Locked In ARC)vor 12 Tagen

LFG🔥🔥

Profilbild von Arpan (Locked In ARC)

Arpan (Locked In ARC)vor 12 Tagen

You will win 🍀

Profilbild von Vaibhav Srivastava

Vaibhav Srivastavavor 12 Tagen

Congratulations 🎊

Profilbild von Rahul Guha

Rahul Guhavor 12 Tagen

I was using @SarvamAI, let's see how this plays out.

Profilbild von rohan

rohanvor 12 Tagen

@SarvamAI let's go

Profilbild von Mad scientist 🥼

Mad scientist 🥼vor 12 Tagen

Congratulations, how can we contribute?

Profilbild von rohan

rohanvor 12 Tagen

Spread the word 🤌

Profilbild von AMBUJ TIWARI

AMBUJ TIWARIvor 12 Tagen

I'll make sure to cover each update from now 🙌

Profilbild von rohan

rohanvor 12 Tagen

hahaha indeed

Profilbild von cheaty

cheatyvor 12 Tagen

took you guys long enough

Profilbild von ∞ Gman

∞ Gmanvor 12 Tagen

Great move to open source it 💪 We should add them to @indos_tech catalog @utkarsh_k1c

Profilbild von Genysis AI

Genysis AIvor 12 Tagen

Great I am happy india is taking root in ai landscape

Profilbild von Samiksha Shukla

Samiksha Shuklavor 12 Tagen

Crazy! Excited to try it out!!

Profilbild von rohan

rohanvor 12 Tagen

lmk how it goes!

Profilbild von pushkar

pushkarvor 12 Tagen

super cool, congratulations on the release!

Profilbild von rohan

rohanvor 12 Tagen

thanks @thepushkarp

Profilbild von Mehar

Meharvor 12 Tagen

never not impressed by rumik. so so good 🙌

Profilbild von Brian Hadu

Brian Haduvor 12 Tagen

if it really beats top closed models, it could shift the landscape for accessibility

Profilbild von himanshu

himanshuvor 12 Tagen

very cool, congrats!

Profilbild von rohan

rohanvor 11 Tagen

tahnks @himanshustwts

Profilbild von Aryan

Aryanvor 12 Tagen

🚀🚀🚀🚀

Profilbild von Kimi Nguyen

Kimi Nguyenvor 12 Tagen

training on just 66k hours and outperforming top models is no small feat

Profilbild von Ayman

Aymanvor 12 Tagen

Congratulations 🎉. Is Bengali trained as well?

Profilbild von rohan

rohanvor 12 Tagen

Yes

Profilbild von Parth

Parthvor 12 Tagen

very cool, congrats on the launch!

Profilbild von aniketh

anikethvor 12 Tagen

never bet against these guys @lets_dig_deeper and @bhartivatsal ❤️

Profilbild von Srinivasa Babu 💙

Srinivasa Babu 💙vor 12 Tagen

It's exciting to know that we have multiple options across different languages, which can now be used as an alternative to Google's live models. Though at this point in time, I would still prefer using Gemini Live because I feel I can make it sound better in Tamil and have the same expressiveness that has been demonstrated here. I am really excited to try this on the next version, though!

Profilbild von Noctus

Noctusvor 12 Tagen

Congrats for the launch

Profilbild von ᱫᱩᱞᱟᱹᱲ

ᱫᱩᱞᱟᱹᱲvor 12 Tagen

does it support Santali?

Profilbild von kartik

kartikvor 12 Tagen

insane🔥, and well detailed blog!

Profilbild von Aru_sharma

Aru_sharmavor 12 Tagen

Let's go congrats for the crazy feat

Profilbild von Krishna Chaturvedi

Krishna Chaturvedivor 12 Tagen

66k hours and these benchmark results is seriously impressive. Great work.🤌

Profilbild von Atharva

Atharvavor 12 Tagen

Incredible timing, I just spent half a day messing with Sarvam to make it sound right. Congrats!

Profilbild von Arib Zeeshan

Arib Zeeshanvor 12 Tagen

This is the first indian AI thing that is actually superior to the other peer products.........I dont know how well it is compared to GPT Live (Its the current SOTA I think), But certainly one of the better open source models from the demos I have seen.

Profilbild von Hrushik Pabbathi

Hrushik Pabbathivor 12 Tagen

yooo that's insane!! congrats!!

Profilbild von Neelakandan NC

Neelakandan NCvor 12 Tagen

Languages are finally becoming our strength

Profilbild von Nipun Taneja

Nipun Tanejavor 12 Tagen

W

Profilbild von Rohan Malik

Rohan Malikvor 12 Tagen

from Rohan to another....keep at it bro...naam roshan karo humara.

Profilbild von Vineeth

Vineethvor 12 Tagen

Lfggggg

Ähnliche Videos

The new open-source Text to Speech model: Fish Speech 1.4 is brilliant! Trained on a massive 700K hours of multilingual speech data in 8 languages - Instant voice cloning 🗣️ - Ultra-low latency ⚡ - Compact model (~1GB weights) 🏋️‍♂️

The new open-source Text to Speech model: Fish Speech 1.4 is brilliant! Trained on a massive 700K hours of multilingual speech data in 8 languages - Instant voice cloning 🗣️ - Ultra-low latency ⚡ - Compact model (~1GB weights) 🏋️‍♂️

Rohan Paul

228,905 Aufrufe • vor 2 Jahren

Introducing Indic-Parler TTS - Trained on 10K hours of data, 938M params, supports 20 Indic languages, emotional synthesis, apache 2.0 licensed! 🔥 A collaboration w/ AI4Bharat & Hugging Face - w/ fully customisable speech and voice personas! Try it out directly below or use the model weights as you want! 🇮🇳/acc

Introducing Indic-Parler TTS - Trained on 10K hours of data, 938M params, supports 20 Indic languages, emotional synthesis, apache 2.0 licensed! 🔥 A collaboration w/ AI4Bharat & Hugging Face - w/ fully customisable speech and voice personas! Try it out directly below or use the model weights as you want! 🇮🇳/acc

Vaibhav (VB) Srivastav

42,212 Aufrufe • vor 1 Jahr

Introducing Ψ₀ ( — an open foundation model for universal humanoid loco-manipulation. 🏆 Outperforms GR00T N1.6 by 40%+ overall success rate 📉 Uses only ~10% of the pre-training data 📦 Fully open-source: model, data, code, and deployment pipeline 1/10

Introducing Ψ₀ ( — an open foundation model for universal humanoid loco-manipulation. 🏆 Outperforms GR00T N1.6 by 40%+ overall success rate 📉 Uses only ~10% of the pre-training data 📦 Fully open-source: model, data, code, and deployment pipeline 1/10

Yue Wang

26,408 Aufrufe • vor 6 Monaten

LETS GOO! Parler TTS 🔥 A fully open-source, Apache 2.0 licensed Text-to-speech model focused on providing maximum controllability. Through voice prompts, you can control the pitch, speed, gender, noise levels, emotion characteristics and more! > Trained on 10K hours of permissive data. > Offers control over the generations. > Training + Inference code released. > The processed dataset and tagging scripts were released for further research. > English only for now. Next, we're scaling the training to 50K hours and even better dataset processing! Want to help us out? DMs open! 🤗

LETS GOO! Parler TTS 🔥 A fully open-source, Apache 2.0 licensed Text-to-speech model focused on providing maximum controllability. Through voice prompts, you can control the pitch, speed, gender, noise levels, emotion characteristics and more! > Trained on 10K hours of permissive data. > Offers control over the generations. > Training + Inference code released. > The processed dataset and tagging scripts were released for further research. > English only for now. Next, we're scaling the training to 50K hours and even better dataset processing! Want to help us out? DMs open! 🤗

Vaibhav (VB) Srivastav

156,386 Aufrufe • vor 2 Jahren

1/n We are excited to announce EchoPrime – the first echocardiography AI model capable of evaluating a full transthoracic echocardiogram study, identify the most relevant videos, and produce a comprehensive interpretation! Great work lead by Milos Vukadinovic, EchoPrime is the largest and most complex #echofirst AI model yet, trained on 10x the data of existing models.

1/n We are excited to announce EchoPrime – the first echocardiography AI model capable of evaluating a full transthoracic echocardiogram study, identify the most relevant videos, and produce a comprehensive interpretation! Great work lead by Milos Vukadinovic, EchoPrime is the largest and most complex #echofirst AI model yet, trained on 10x the data of existing models.

David Ouyang, MD

155,571 Aufrufe • vor 1 Jahr

LETS GOOO! FishSpeech v1.5 - multilingual, zero-shot instant voice cloning, low-latency, open text to speech model 🔥 > Only 500M params > Trained on 1 MILLION hours of audio > Supports 13 languages > Low-latency ( Open model - checkpoints on the hub 🤗 > Best part: Ranks #2 on TTS Arena (preliminary results) Kudos to Fish Audio - truly leading the way for open text to speech research! ⚡

LETS GOOO! FishSpeech v1.5 - multilingual, zero-shot instant voice cloning, low-latency, open text to speech model 🔥 > Only 500M params > Trained on 1 MILLION hours of audio > Supports 13 languages > Low-latency ( Open model - checkpoints on the hub 🤗 > Best part: Ranks #2 on TTS Arena (preliminary results) Kudos to Fish Audio - truly leading the way for open text to speech research! ⚡

Vaibhav (VB) Srivastav

49,150 Aufrufe • vor 1 Jahr

Today we are introducing Dyna-2, a world-action model pre-trained on one million hours of human video. At this scale, for the first time, we discovered several new scaling laws: • world-action models exhibit scaling law on human data across four orders of magnitude, from 1000 to 1,000,000 hours, • this human data scaling law implied a scaling law on never seen robot data, • both data and objective matter; world modeling and scaling on video data are essential for cross-embodiment scaling transfer to emerge 🧵

Today we are introducing Dyna-2, a world-action model pre-trained on one million hours of human video. At this scale, for the first time, we discovered several new scaling laws: • world-action models exhibit scaling law on human data across four orders of magnitude, from 1000 to 1,000,000 hours, • this human data scaling law implied a scaling law on never seen robot data, • both data and objective matter; world modeling and scaling on video data are essential for cross-embodiment scaling transfer to emerge 🧵

Dyna Robotics

1,794,709 Aufrufe • vor 1 Monat

Introducing TranslatePsy-AfriSLM: state-of-the-art machine translation for 19 Sub-Saharan African languages using models small enough to run on a laptop or a smartphone. Our smallest LM, at just 0.8B parameters, matches or beats systems up to 152 times its size, including Qwen3.5-122B-A10B and TranslateGemma-27B, on 3 key benchmarks. Models: Research Paper: Blog:

Introducing TranslatePsy-AfriSLM: state-of-the-art machine translation for 19 Sub-Saharan African languages using models small enough to run on a laptop or a smartphone. Our smallest LM, at just 0.8B parameters, matches or beats systems up to 152 times its size, including Qwen3.5-122B-A10B and TranslateGemma-27B, on 3 key benchmarks. Models: Research Paper: Blog:

QVAC

386,787 Aufrufe • vor 18 Tagen

Introducing GLM 5.2 for autoresearch GLM 5.2 is the first open weights model we've tried on our autoresearch pipeline that's proven capable for real research tasks. With Fable 5's restrictions on research, having an open weights alternative is a huge win for open source Watch it carry out fully async vs colocated sync RL training on Harbor code contests across two 8xH100 nodes on top of SkyRL. Resolves setup issues, tracks runs to completion, and produces a full comparison of throughput and reward stability

Introducing GLM 5.2 for autoresearch GLM 5.2 is the first open weights model we've tried on our autoresearch pipeline that's proven capable for real research tasks. With Fable 5's restrictions on research, having an open weights alternative is a huge win for open source Watch it carry out fully async vs colocated sync RL training on Harbor code contests across two 8xH100 nodes on top of SkyRL. Resolves setup issues, tracks runs to completion, and produces a full comparison of throughput and reward stability

alphaXiv

271,866 Aufrufe • vor 3 Monaten

Introducing Scribe — the most accurate Speech to Text model. It has the highest accuracy on benchmarks, outperforming previous state-of-the-art models such as Gemini 2.0 and OpenAI Whisper v3. It’s now the leading model for English, Spanish, Italian, and many more. With support for 99 languages, speaker diarization, character-level timestamps, and non-speech events such as laughing.

Introducing Scribe — the most accurate Speech to Text model. It has the highest accuracy on benchmarks, outperforming previous state-of-the-art models such as Gemini 2.0 and OpenAI Whisper v3. It’s now the leading model for English, Spanish, Italian, and many more. With support for 99 languages, speaker diarization, character-level timestamps, and non-speech events such as laughing.

ElevenLabs

464,967 Aufrufe • vor 1 Jahr

Mfw Minimax H3, the new Open Source Audiovisual model that is vastly superior to all the Frontier models, is also the first model in history to be trained on and remember The Will Stancil Show and now chooses to generate propaganda posters of Will Stancil all on its own.

Mfw Minimax H3, the new Open Source Audiovisual model that is vastly superior to all the Frontier models, is also the first model in history to be trained on and remember The Will Stancil Show and now chooses to generate propaganda posters of Will Stancil all on its own.

Emily Youcis

13,539 Aufrufe • vor 1 Monat

#WATCH | Bengaluru, Karnataka: Co-founder, Sarvam AI, Pratyush Kumar says, "... It's been three years now. We started off building on top of the Llama model, which was the best open model at that time. Sarvam was the only company outside, or maybe in Asia, that contributed to the Llama 3 Series. We understood how to add language skills into models, and Llama 3 was reasonable in Indian languages. When the first set of GPUs arrived in India, we pre-trained from scratch a 2-billion model and worked with Infosys to make it useful for IT services. Then we recognised the importance of scaling up reinforcement learning and built a reasoning model called Sarvam M on top of Mistral's small model. Over the last year, we pre-trained from scratch in India on 4,000 Hopper Series GPUs a 100-billion-plus-parameter model..."

#WATCH | Bengaluru, Karnataka: Co-founder, Sarvam AI, Pratyush Kumar says, "... It's been three years now. We started off building on top of the Llama model, which was the best open model at that time. Sarvam was the only company outside, or maybe in Asia, that contributed to the Llama 3 Series. We understood how to add language skills into models, and Llama 3 was reasonable in Indian languages. When the first set of GPUs arrived in India, we pre-trained from scratch a 2-billion model and worked with Infosys to make it useful for IT services. Then we recognised the importance of scaling up reinforcement learning and built a reasoning model called Sarvam M on top of Mistral's small model. Over the last year, we pre-trained from scratch in India on 4,000 Hopper Series GPUs a 100-billion-plus-parameter model..."

ANI

163,060 Aufrufe • vor 1 Monat

Introducing DINOv3: a state-of-the-art computer vision model trained with self-supervised learning (SSL) that produces powerful, high-resolution image features. For the first time, a single frozen vision backbone outperforms specialized solutions on multiple long-standing dense prediction tasks. Learn more about DINOv3 here:

Introducing DINOv3: a state-of-the-art computer vision model trained with self-supervised learning (SSL) that produces powerful, high-resolution image features. For the first time, a single frozen vision backbone outperforms specialized solutions on multiple long-standing dense prediction tasks. Learn more about DINOv3 here:

AI at Meta

901,265 Aufrufe • vor 1 Jahr

🚀 Galbot just released AstraBrain-WBC 0.5, the world’s first humanoid robot cerebellum foundation model. Trained on 20,000 hours of human motion data, it validates a Scaling Law for robot motion control and demonstrates zero-shot execution of unseen motions on real humanoids. The era of robot control foundation models is getting closer.

🚀 Galbot just released AstraBrain-WBC 0.5, the world’s first humanoid robot cerebellum foundation model. Trained on 20,000 hours of human motion data, it validates a Scaling Law for robot motion control and demonstrates zero-shot execution of unseen motions on real humanoids. The era of robot control foundation models is getting closer.

Eren Chen

10,270 Aufrufe • vor 3 Monaten

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗

Vaibhav (VB) Srivastav

79,645 Aufrufe • vor 1 Jahr

- <1B params - supports 91 languages - 5 pages/s on RTX 5090 - runs on CPU, GPU, MPS - 83.3% olmocr bench score (top under 3B) Surya OCR is a state-of-the-art model for document intelligence. 100% open-source.

- <1B params - supports 91 languages - 5 pages/s on RTX 5090 - runs on CPU, GPU, MPS - 83.3% olmocr bench score (top under 3B) Surya OCR is a state-of-the-art model for document intelligence. 100% open-source.

Akshay 🚀

63,902 Aufrufe • vor 3 Monaten